[Xen-devel] Measuring intra-CPU stime skew

["Dan Magenheimer" <dan.magenheimer@xxxxxxxxxx>]

With the attached patch, I am trying to measure maximum
intra-CPU stime skew.  This is not (necessarily) intended
to be applied, but I'd be very interested in review to
see if I am measuring it accurately or if there might
be other more accurate methods than these three.

I'd also be interested in measurements from other machines
and configurations.  (Output obtained with "xm debug-key t"
which can be iterated in a shell loop to collect samples
for one of the collection methods... they others are
collected automatically.)

If it is accurate, skew is worse than I had previously
thought.  Not horribly worse, but I am seeing 30-40us
skew (on hpet) instead of the 11us I was seeing before.

Thanks,
Dan


===================================
Thanks... for the memory
I really could use more / My throughput's on the floor
The balloon is flat / My swap disk's fat / I've OOM's in store
Overcommitted so much
(with apologies to the late great Bob Hope)

Attachment: recordskew.patch
Description: Binary data

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel